Meta-Llama-3.1-8B-Instruct-abliterated/README.md

license, library_name, tags, base_model, model-index

license	library_name	tags	base_model	model-index
llama3.1	transformers	abliterated uncensored	meta-llama/Meta-Llama-3.1-8B-Instruct	name results Meta-Llama-3.1-8B-Instruct-abliterated task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 73.29 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 27.13 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 6.42 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 0.89 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 3.21 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 27.81 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated Open LLM Leaderboard

🦙 Meta-Llama-3.1-8B-Instruct-abliterated

🦙 Llama 3.1 70B Instruct lorablated

This is an uncensored version of Llama 3.1 8B Instruct created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

⚡️ Quantization

Thanks to ZeroWw and Apel-sin for the quants.

• New GGUF: https://huggingface.co/mlabonne/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
• ZeroWw GGUF: https://huggingface.co/ZeroWw/Meta-Llama-3.1-8B-Instruct-abliterated-GGUF
• EXL2: https://huggingface.co/Apel-sin/llama-3.1-8B-abliterated-exl2

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	23.13
IFEval (0-Shot)	73.29
BBH (3-Shot)	27.13
MATH Lvl 5 (4-Shot)	6.42
GPQA (0-shot)	0.89
MuSR (0-shot)	3.21
MMLU-PRO (5-shot)	27.81